Skip to main content
Glama

reach_svhc_threshold_screener

Read-onlyIdempotent

[REACH Candidate List SVHC 0.1% threshold screener. Deterministic calculation, read-only, side-effect free]. Audits candidate list SVHC concentration by weight (w/w) in complex articles ex ECJ Case C-106/14 (Once an Article, Always an Article), identifying mandatory Article 33 supply chain duty and Article 7(2) ECHA notifications. Usage: Submit complex article components and substance masses to calculate component-level and article-level concentrations. Returns: JSON object with { articleName: string, totalCalculatedMassGrams: number, isArticleSubjectToArt33Communication: boolean, isScipNotificationMandatory: boolean, componentAudits: array }.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "articleName": "<articleName>",
      "components": "<components>"
    },
    "name": "reach_svhc_threshold_screener"
  }
}

Input Schema

NameRequiredDescriptionDefault
componentsYesComponents comprising the article under the O5A principle
articleNameYesArticle trade or engineering name
totalArticleMassGramsNoTotal mass of article in grams (defaults to sum of components)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.6/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and idempotentHint, and the description largely restates this ('Deterministic calculation, read-only, side-effect free'), adding only the determinism guarantee. It does add value by enumerating the returned JSON fields, which matters because no output schema exists, but it stays silent on limits such as CAS-number validation, handling of trace/impurity mass, or non-legal-advice caveats.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three front-loaded blocks (purpose, usage, returns) with no filler sentences, and the return shape is listed compactly rather than prose-wrapped. The bracketed tag partly duplicates the annotations, which is minor waste but not harmful.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly carries the return contract by listing the audit fields, and it covers the calculation's legal basis and scope of the input. What remains thin is the boundary to adjacent REACH tools (SCIP dossier, FCM screener) and any assumptions about substance identification.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline would be 3; the description earns an increment by framing the input model itself — complex articles decomposed into components with per-substance masses, audited at both component and article level. That conceptual framing helps an agent structure nested payloads correctly even though field-level semantics live in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a precise verb and resource: auditing SVHC concentration by weight in complex articles under the Once-an-Article-Always-an-Article principle, with the 0.1% threshold and Article 33/Article 7(2) consequences named. It never names a sibling such as scip_notification_dossier_screener, and the mention of notification duties could plausibly blur the line with that tool, so it stops short of full sibling differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The 'Usage' line tells the agent what to submit (article components and substance masses) to obtain component-level and article-level concentrations, which implies the invocation context. It gives no when-not conditions, no prerequisites (e.g., that substances must already be identified as Candidate List entries), and no routing to the SCIP dossier sibling for downstream notification.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources